Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1956 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.6076. Min Act: -0.1700
Data Index: 7154579 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.3576. Min Act: -0.1700
Data Index: 7628188 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.1701. Min Act: -0.1700
Data Index: 4951442 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.0451. Min Act: -0.1700
Data Index: 2763399 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.8889. Min Act: -0.1700
Data Index: 5614164 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.8264. Min Act: -0.1700
Data Index: 3631821 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.8264. Min Act: -0.1700
Data Index: 3727520 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.8264. Min Act: -0.1700
Data Index: 6570062 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.8264. Min Act: -0.1700
Data Index: 6177045 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7951. Min Act: -0.1700
Data Index: 543390 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7639. Min Act: -0.1700
Data Index: 7831564 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7639. Min Act: -0.1700
Data Index: 1418001 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7639. Min Act: -0.1700
Data Index: 61829 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7326. Min Act: -0.1700
Data Index: 3859204 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7326. Min Act: -0.1700
Data Index: 3196813 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7326. Min Act: -0.1700
Data Index: 1302206 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7014. Min Act: -0.1700
Data Index: 2555762 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.6701. Min Act: -0.1700
Data Index: 889851 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.6701. Min Act: -0.1700
Data Index: 6135550 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.6389. Min Act: -0.1700
Data Index: 4787818 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19